The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from existing repository files to determine the current project configuration, which could potentially contain untrusted instructions if modified by external parties.
Ingestion points: Reads content from CLAUDE.md, AGENTS.md, and GLOSSARY.md during the exploration phase.
Boundary markers: The skill requires explicit user confirmation before writing or updating any files, acting as a manual checkpoint.
Capability inventory: File system read/write access and execution of standard command-line tools like git, gh, and glab.
Sanitization: The skill does not explicitly sanitize the content of the files it reads, but it presents a summary to the user for validation.
[COMMAND_EXECUTION]: The skill instructs the agent to execute standard developer commands to inspect the repository environment and provides templates for managing issues via CLI tools.
Evidence: Execution of git remote -v and templates for using the GitHub (gh) and GitLab (glab) CLI tools for issue tracking operations.
[EXTERNAL_DOWNLOADS]: The documentation references an official development tool for repository management.
Evidence: Provides a link to the official GitLab CLI repository (https://gitlab.com/gitlab-org/cli) within the GitLab tracker documentation.

setup-matt-pocock-skills